Comparison of the Effectiveness of AI Models in Poker Games
Journal of Eastern Europe Research in Business and Economics · 09.04.2026
DOI: 10.5171/2025.4534725 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Eastern Europe Research in Business and Economics, online erschienen am 09.04.2026. Verfasst von Mateusz TUSTANOWSKI und 1 weiteren Autor:innen.
Abstract (Originalsprache)
In this investigation, we evaluate the comparative efficacy of Random Forest (RF) classifiers and Deep Q-Network (DQN) agents in the context of No-Limit Texas Hold’em poker. Within a high-fidelity simulation, RF-based agents—trained through supervised learning on labeled gameplay data—demonstrated superior and more consistent profitability relative to their DQN counterparts, which were optimized via reinforcement learning [1, 2, 3]. The DQN models exhibited pronounced performance volatility and were particularly susceptible to variations in hyperparameter configuration [10]. These findings indicate that supervised approaches confer greater robustness in this domain [15]. Moreover, we propose that an integrated methodology—employing RF pretraining to establish a reliable baseline, followed by DQN fine-tuning to introduce adaptability—may yield an optimal trade-off between stability and learning flexibility.
Zitieren
APA
TUSTANOWSKI, M., & WOZNIAK, A. P. (2026). Comparison of the Effectiveness of AI Models in Poker Games. Journal of Eastern Europe Research in Business and Economics. https://doi.org/10.5171/2025.4534725
Vancouver
TUSTANOWSKI M, WOZNIAK AP. Comparison of the Effectiveness of AI Models in Poker Games. Journal of Eastern Europe Research in Business and Economics. 2026. doi:10.5171/2025.4534725
BibTeX
@article{TUSTANOWSKI2026,
author = {TUSTANOWSKI, Mateusz and WOZNIAK, Adrian P.},
title = {Comparison of the Effectiveness of AI Models in Poker Games},
journal = {Journal of Eastern Europe Research in Business and Economics},
year = {2026},
doi = {10.5171/2025.4534725}
}
EUVIMED